© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17194
    Prev
    Next
    INDEX
    Explanations

    analyze and investigate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unp
    -0.09
     forever
    -0.09
     peril
    -0.09
     discipline
    -0.09
    ETO
    -0.09
    488
    -0.08
     plural
    -0.08
     unarmed
    -0.08
     enth
    -0.08
     pars
    -0.08
    POSITIVE LOGITS
     analysis
    0.14
     analysed
    0.12
     analyse
    0.12
     observation
    0.12
     analys
    0.12
     clearly
    0.12
     analyzed
    0.11
    noticed
    0.11
     analyzing
    0.11
     Noticed
    0.11
    Activations Density 0.173%

    No Known Activations